شناسایی آسیب ساختاری بر اساس شبکه های عصبی خودرمزنگار
Abstract
1- Introduction
2- Autoencoder based framework for structural health monitoring
3- Numerical studies
4- Experimental verifications
5- Conclusion
References
Abstract
Artificial neural networks are computational approaches based on machine learning to learn and make predictions based on data, and have been applied successfully in diverse applications including structural health monitoring in civil engineering. It is difficult to optimize the weights in the neural networks that have multiple hidden layers due to the vanishing gradient issue. This paper proposes an autoencoder based framework for structural damage identification, which can support deep neural networks and be utilized to obtain optimal solutions for pattern recognition problems of highly non-linear nature, such as learning a mapping between the vibration characteristics and structural damage. Two main components are defined in the proposed framework, namely, dimensionality reduction and relationship learning. The first component is to reduce the dimensionality of the original input vector while preserving the required necessary information, and the second component is to perform the relationship learning between the features with the reduced dimensionality and the stiffness reduction parameters of the structure. Vibration characteristics, such as natural frequencies and mode shapes, are used as the input and the structural damage are considered as the output vector. A pre-training scheme is performed to train the hidden layers in the autoencoders layer by layer, and fine tuning is conducted to optimize the whole network. Numerical and experimental investigations on steel frame structures are conducted to demonstrate the accuracy and efficiency of the proposed framework, comparing with the traditional ANN methods.
Introduction
Civil infrastructure including bridges and buildings etc., are crucial for a society to well function. They may deteriorate progressively and accumulate damage during their service life due to fatigue, overloading and extreme events, such as strong earthquake and cyclones. Structural Health Monitoring (SHM) provides practical means to assess and predict the structural performance under operational conditions. It is usually referred as the measurement of the critical responses of a structure to track and evaluate the symptoms of operational incidents, anomalies, and deterioration that may affect the serviceability and safety [1]. Numerous efforts have been devoted to develop vibration based structural damage identification methods by using vibration characteristics of structures [2]. These methods are based on the fact that changes in the structural physical parameters, such as stiffness and mass, will alter the structural vibration characteristics as well, i.e. natural frequencies and mode shapes. Structural damage identification based on changes in vibration characteristics of structures can be formulated as a pattern-recognition problem. One of the most significant challenges associated with the vibration based methods is that they are susceptible to uncertainties in the damage identification process, such as, finite element modelling errors, noises in the measured vibration data and environmental effect etc. Artificial intelligence techniques, such as Artificial Neural networks (ANN) [3] and Genetic Algorithms (GA) [4], and Swarm Intelligence methods [5,6] are computational approaches based on machine learning to learn and make predictions based on data, and have been applied successfully in diverse applications including SHM in civil engineering. Yun et al. [7] estimated the structural joint damage from modal data via an ANN model. Noise injection learning with a realistic noise level for each input component was found to be effective in better understanding the noise effect in this work. Later, the mode shape differences or the mode shape ratios before and after damage were used as the input to the neural networks to reduce the effect of the modelling errors in the baseline finite element model.